Kick-Start
Sand Tracer | Following Dune Dynamics from Space
This project develops Sand Tracer, a satellite-based service that monitors sand movement in coastal dunes to support Nature-Based Solutions for biodiversity and coastal resilience. Insight in sand displacement provides vital data to support conservation and sustainable ecosystem management.
Executive Summary
Sand Tracer provides an innovative solution for monitoring sand dynamics in dune ecosystems. The service leverages high-resolution satellite imagery and LiDAR data, coupled with advanced AI algorithms, to map and measure sand displacement volumes, offering a comprehensive and timely understanding of dune evolution.
Services: Sand Tracer delivers precise measurements of sand displacement volumes, identifies erosion and accretion hotspots, and tracks changes in dune morphology over time.
Market opportunity: This service addresses the growing demand for effective biodiversity monitoring and coastal resilience strategies. Target users include:
- Environmental Agencies: To assess the impact of management practices on dune ecosystems.
- Coastal Managers: To support coastal resilience strategies and assess erosion risks.
- Research Institutions: To study dune dynamics and their ecological implications.
Customers/Users: Key partners engaged in the project include: [Current status: not fixed]
- Name of organization. Residing in the Netherlands.
- Name of organization. Residing in Belgium.
- Name of organization. Residing in France.
- Name of organization. Residing in Portugal.
Customer need/problem: Existing methods for monitoring dune dynamics, such as manual surveys and infrequent LiDAR campaigns, are expensive, time-consuming and lack the temporal resolution needed for effective management.
Bidder and partner motivation: HKV, with its proven expertise in remote sensing, AI, and coastal dynamics, is committed to developing an operational service for biodiversity monitoring and coastal resilience. Our partners, representing key stakeholders, are motivated by the potential of Sand Tracer to improve their management practices and contribute to achieving biodiversity and coastal resilience goals.
Space assets involved: Sand Tracer relies on high-resolution satellite imagery from providers such as Planet and the European Copernicus programme. Additionally, LiDAR data from national and international sources will be incorporated to enhance the accuracy of sand volume estimations.
Business Potential
Business model
[Current status: To be filled in based on Business Model Canvas]
Customer/users and stakeholders
Customer/user organisations planned to be involved in the activity [Current status: not fixed]:
- Name of organization. Motivation of organization.
- Name of organization. Motivation of organization.
- Name of organization. Motivation of organization.
- Name of organization. Motivation of organization.
Motivation:
These organisations are all actively involved in managing and monitoring dune ecosystems, driven by the goals of preserving biodiversity and ensuring coastal safety. They recognise the potential of Sand Tracer to provide them with:
Improved monitoring capabilities: Sand Tracer offers a cost-effective and efficient solution for monitoring sand dynamics across large areas, enabling them to better track the effectiveness of their management practices.
Data-driven decision making: The service provides valuable insights into erosion and accretion patterns, supporting evidence-based decision-making for habitat restoration, dune reinforcement, and coastal resilience.
Enhanced reporting and compliance: Sand Tracer facilitates the generation of quantitative data on dune dynamics, supporting their reporting obligations related to biodiversity targets and coastal management strategies.
Approach for Engagement:
We will actively engage with these customers/users through:
Collaborative workshops: To gather user requirements, co-design service features, and ensure the service meets their specific needs.
Regular feedback sessions: To collect feedback on service performance, address user concerns, and continuously improve the service based on their input.
Dissemination of results: To showcase the value of Sand Tracer through reports, presentations, and online platforms, demonstrating its potential to a broader audience.
We will leverage our existing network within the KRING to reach additional potential customers, including other nature management organisations, research institutions, and consultancies involved in coastal management and biodiversity monitoring.
Gap analysis
Sand Tracer targets a market with a significant and growing demand for effective biodiversity monitoring and coastal management solutions. The following trends drive this demand:
- Increasing focus on biodiversity conservation: Globally, there is a growing recognition of the importance of biodiversity and the need to monitor and conserve ecosystems effectively. This is reflected in international agreements like the Kunming-Montreal Global Biodiversity Framework, which sets ambitious targets for biodiversity conservation.
- Climate change and coastal vulnerability: Coastal areas are increasingly vulnerable to the impacts of climate change, including sea-level rise, increased storm surges, and coastal erosion. Sand dunes play a crucial role in coastal resilience, making monitoring their dynamics essential for assessing risks and implementing adaptation strategies.
- Demand for data-driven decision making: There is a growing demand for evidence-based decision-making in environmental management, driven by the need for accountability, transparency, and effective resource allocation. Sand Tracer provides quantitative data on dune dynamics, supporting data-driven approaches to coastal management.
Market demand and customer/user needs
While several companies offer remote sensing services for environmental monitoring, Sand Tracer differentiates itself by focusing on precise and high-frequency monitoring of sand dynamics in dune ecosystems. Our key competitive advantages include:
- Domain expertise: HKV has a strong track record in coastal dynamics, hydrology, and nature-based solutions, combined with expertise in remote sensing and AI.
- User-centric approach: We prioritize close collaboration with end-users to ensure the service meets their specific needs and integrates seamlessly into their workflows.
- Scalability and international potential: Sand Tracer is designed to be scalable and adaptable to different dune environments, offering potential for international expansion.
Value proposition
Sand Tracer offers a compelling value proposition for its target customers by providing:
- Cost-effective monitoring: Replacing expensive and time-consuming manual surveys with automated satellite-based monitoring, significantly reducing costs and increasing efficiency.
- High-frequency data: Providing frequent updates on sand dynamics, enabling timely detection of changes and rapid response to erosion events or habitat degradation.
- Actionable insights: Delivering clear and concise information on sand displacement volumes, erosion hotspots, and dune morphology changes, supporting informed decision-making for habitat management and coastal resilience.
Value chain and positioning
Sand Tracer will be positioned as a key service provider within the value chain for dune ecosystem monitoring and coastal management. The value chain typically includes:
- Data acquisition: Obtaining high-resolution satellite imagery and LiDAR data from various sources.
- Data processing and analysis: Applying AI algorithms to extract information on sand dynamics, generate maps, and quantify sand displacement volumes.
- Information delivery: Providing users with accessible and user-friendly visualizations, reports, and alerts based on the analysed data.
- Decision support and action: Enabling users to make informed decisions about habitat restoration, dune reinforcement, and coastal resilience strategies based on the insights provided.
HKV will focus on data processing and analysis, information delivery, and decision support, leveraging our expertise in remote sensing, AI, and coastal dynamics. We will establish partnerships with data providers, such as Planet and Copernicus, to ensure access to high-quality satellite imagery.
Partnerships:
- Data providers: Collaboration with satellite imagery providers (e.g., Planet, Copernicus) to secure access to necessary data.
- Software developers: Partnerships with software companies to integrate Sand Tracer into existing platforms used by target customers.
- Research institutions: Collaboration with universities and research centres to validate the methodology and explore further applications.
Commercial Risks:
- Market adoption: The success of Sand Tracer depends on the willingness of potential users to adopt satellite-based monitoring solutions and integrate them into their existing workflows.
- Data availability and cost: Access to high-resolution satellite imagery and LiDAR data at reasonable costs is crucial for the service’s sustainability.
- Competition: The emergence of new competitors offering similar services could impact market share and profitability.
Technical part
Application/service
Sand Tracer is a web-based application that utilizes satellite data and AI algorithms to monitor sand dynamics in dune ecosystems. The service provides users with the following outputs:
Sand displacement maps: Visual representations of sand movement within the dune area, highlighting areas of erosion and accretion.
Sand volume estimations: Quantitative measurements of sand volumes displaced over time, providing insights into the magnitude of erosion and accretion processes.
Change detection analysis: Identification of significant changes in dune morphology, such as the formation or disappearance of blowouts (in dutch: stuifkuilen), based on time-series analysis of satellite and LiDAR data.
Use the slider to explore the time period from 2019 to 2024. This false-color timelapse uses IRG channels mapped to RGB and combines high-resolution data from SuperView-1 (0.5m), SuperView-NEO (0.3m), and Pleiades-NEO (0.3m). The location corresponds to quadkey 12020211001311100 with an approximate spatial resolution of 1m.
System Architecture:
Data acquisition: High-resolution satellite imagery (e.g., Planet, Sentinel-2) and LiDAR data (e.g., AHN) are acquired for the area of interest.
Pre-processing: Integration enabled for processing satellite images and LiDAR data within the data management system.
Sand surface segmentation: AI algorithms are used to segment the sand surface from other land cover types in the satellite images, generating accurate boundaries of the dune area.
Volume calculation: Sand volume changes are calculated using LiDAR point clouds and an innovative technique to extract height information from optical satellite images, allowing for higher temporal resolution monitoring.
Integration with wind data: Sand Tracer incorporates wind data to provide context for sand movement patterns, helping users understand the driving forces behind dune dynamics.
Visualization and analysis: The processed data is visualized in a user-friendly web interface, allowing users to explore sand displacement maps, volume estimations, and change detection results.
Technical Requirements:
High-resolution satellite imagery: Images with a spatial resolution of less than 5 meters are required to capture detailed dune morphology.
LiDAR Data: Point cloud data with a high point density is necessary for accurate elevation measurements and volume calculations.
Cloud computing infrastructure: A robust cloud infrastructure is required to handle the large volumes of data and execute computationally intensive AI algorithms.
Secure data storage: Secure storage solutions are essential to ensure the confidentiality and integrity of the data.
Degree of innovation
Sand Tracer introduces several innovative elements compared to state-of-the-art dune monitoring approaches:
Integration of satellite and LiDAR data: The combined use of satellite imagery and LiDAR data leverages the strengths of both technologies, providing both high spatial resolution and frequent temporal coverage.
AI-powered sand dynamics analysis: Advanced AI algorithms are utilized to automate sand surface segmentation, volume calculation, and change detection, significantly increasing efficiency and accuracy compared to manual methods.
High-frequency monitoring: By extracting height information from optical satellite images, Sand Tracer enables monitoring of dune dynamics at a much higher frequency than traditional LiDAR campaigns, allowing for timely detection of changes and rapid response to events.
Involvement of space assets
Here we illustrate the specific space assets that will be used in the Sand Tracer service and justifies their added value.
- SatEO (Satellite Earth Observation): Sand Tracer will use very high-resolution satellite images from the Satellietdataportaal to segment white dune habitats, detect and monitor blowouts, and estimate sand drift volumes.
- Added value: SatEO provides frequent, large-scale coverage that is more cost-effective than traditional methods like aerial photography and field surveys, which have limited spatial coverage and are expensive and time-consuming.
- Specific aspects: While the specific satellites and sensors are not named, the project requires consistent high-resolution imagery for accurate AI analysis.
- LiDAR (Light Detection and Ranging): LiDAR point clouds from the AHN (Algemeen Hoogtebestand Nederland) will be used with the satellite imagery to quantify sand volume differences more accurately.
- Added value: LiDAR offers highly accurate elevation data, which is essential for calculating sand volume changes. Non-space alternatives, such as manual field measurements, are labor-intensive and error-prone.
- Specific aspects: Well-calibrated LiDAR products are required, and improved metadata about flight times is needed to match the LiDAR data with the satellite images accurately.
Competing non-space technologies and their shortcomings:
- AHN data: Though valuable, AHN data is only available annually.
- Jarkusraaien: This method is labor-intensive, expensive, and offers limited spatial coverage.
- Field measurements: These measurements are localized, time-consuming, and expensive on a large scale.
By integrating SatEO and LiDAR data, Sand Tracer provides significant advantages over traditional methods, enabling efficient, comprehensive, and cost-effective monitoring of dune dynamics for better biodiversity management.
Access to space asset(s)/know-how
Access to the space assets and relevant know-how
Satellite data: HKV uses very high-resolution satellite images obtained through the Satellietdataportaal. The company has developed a pipeline to download satellite data in tiles with fixed dimensions and locations using quadkeys, which code square areas in longitude and latitude. This pipeline ensures a scalable process for acquiring the necessary satellite imagery.
LiDAR data: Sand Tracer utilizes LiDAR point clouds from the AHN (Algemeen Hoogtebestand Nederland) initiative for quantifying sand volume differences. HKV acknowledges the importance of well-calibrated LiDAR products and is seeking improved metadata regarding flight times to enhance the temporal matching between satellite images and LiDAR data.
Wind data: While the specific source of wind data isn’t explicitly mentioned, Sand Tracer incorporates wind information in its analysis. It’s likely that this data is obtained from publicly available sources like the KNMI (Royal Netherlands Meteorological Institute).
AI and Data Science expertise: HKV possesses significant expertise in AI and data science, crucial for developing and implementing Sand Tracer. The company employs specialists in processing and analysing large satellite datasets, developing machine learning algorithms, and building user-friendly interfaces.
Partnerships: HKV collaborates with the KRING, a network of dune managers and nature conservation organisations. This partnership provides valuable domain knowledge, insights into user needs, and access to potential customers.
By combining access to space assets (satellite and LiDAR data) with their in-house expertise in AI and data science and leveraging strategic partnerships, HKV has established a solid foundation for developing and implementing the Sand Tracer service.
Technology maturity
Current development status:
- Sand Tracer is currently progressing from TRL 4-5 to TRL 6-7.
- Technical feasibility has been demonstrated in laboratory conditions and on a small scale, showing that white dune habitat type can be segmented at a spatial resolution of approximately 1x1 meter with consistent high-resolution satellite images.
- AI algorithms have been developed for segmenting sand drifts from other land uses in satellite images.
- A prototype is being developed with functional features based on user stories and feedback from stakeholders.
- Stakeholder readiness is being assessed to ensure end-users are prepared to implement Sand Tracer in a learning year.
Timeline for operational maturity:
- With this call we aim to operationalise Sand Tracer, with a target TRL of 9.
- At least one partner is expected to use Sand Tracer at the end of this Kick Start call.
- Full operational maturity is anticipated within 2 years.
Potential feasibility of the application/service concept
Technical feasibility:
It is feasible to determine the spread of sand drift in dune areas based on very high-resolution satellite images and fusion with LiDAR measurements. Sand Tracer uses high-resolution satellite images, LiDAR elevation measurements, and wind data combined by AI to detect and monitor blowouts and estimate sand drift volumes over time and space. The results show a strong influence of sand drift on the shape of the dune landscape, which in turn affects biodiversity and coastal resilience.
Identification of main technical risks:
Accuracy of sand volume estimations: Ensuring the accuracy of sand volume calculations based on optical satellite imagery requires robust algorithms and validation against ground truth data.
Availability and quality of LiDAR data: Access to high-quality and regularly updated LiDAR data is crucial for the service. Inconsistencies or inaccuracies in the LiDAR data could affect the reliability of the results.
Computational demands: Processing large volumes of satellite and LiDAR data requires significant computational power. Optimizing algorithms and leveraging efficient cloud infrastructure is essential to manage computational demands and ensure timely service delivery.
Risk mitigation strategies:
Algorithm validation: Rigorous validation of AI algorithms against ground truth data will be conducted to assess and improve the accuracy of sand volume estimations.
Data quality control: Strict quality control procedures will be implemented for both satellite and LiDAR data to ensure data integrity and consistency.
Cloud infrastructure optimization: A scalable and efficient cloud infrastructure will be utilized to manage computational demands and ensure timely processing of data.
Work approach to service architecture definition and implementation
Service concept development:
User requirements elicitation: Conduct workshops and interviews with target users to thoroughly understand their specific needs and challenges related to dune monitoring.
Service feature definition: Based on user requirements, define a comprehensive set of service features, including data outputs, visualization options, analytical tools, and reporting capabilities.
System design: Design a robust and scalable system architecture, considering data acquisition, processing, storage, visualization, and user interface components.
Implementation:
Agile development: Employ an agile software development methodology to ensure iterative development, continuous testing, and flexibility to adapt to changing user needs.
Cloud infrastructure deployment: Utilize a cloud-based infrastructure to ensure scalability, reliability, and accessibility of the service.
Algorithm development and validation: Develop and validate AI algorithms for sand surface segmentation, volume calculation, and change detection using a combination of satellite and LiDAR data.
User interface design: Create a user-friendly and intuitive interface that allows users to easily access and interact with the service’s features.
Challenges:
Meeting diverse user needs: Balancing the specific needs of different user groups, such as those focused on nature conservation versus coastal resilience.
Data integration and interoperability: Ensuring seamless integration of data from various sources (satellites, LiDAR, meteorological stations) with different formats and resolutions.
Algorithm accuracy and robustness: Developing AI algorithms that are accurate, robust, and can handle the variability and complexity of dune environments.
Key implementation aspects:
Modular design: Implement a modular system architecture that allows for flexibility and future expansion of service features.
Open-source technologies: Utilize open-source technologies where appropriate to ensure transparency and foster community contributions.
Continuous improvement: Establish a feedback loop with users to collect input and continuously improve the service based on their evolving needs.
Team and resources
Team composition
The Sand Tracer project team comprises highly skilled professionals from HKV with expertise in remote sensing, AI, coastal dynamics, software development, and user engagement:
Key personnel:
Mattijn van Hoek (PhD): Project leader. Extensive experience in processing and analysing large volumes of satellite data, a strong advocate for Machine Learning applications, and a deep understanding of biodiversity in data science.
Michelle Rudolph (MSc, MA): User lengagement lead. Specialist in combining technical and social perspectives, with expertise in Nature-based Solutions, stakeholder engagement, and climate change adaptation. Skilled in facilitating interactive workshops and translating research results into clear visuals.
Thomas Stolp (MSc.): AI specialist. Experienced in developing algorithms utilizing spatial data and Machine Learning techniques. Responsible for building the AI models within the project.
Ron Bruijns (MSc.): Data processing expert. Highly experienced in handling large datasets and applying AI techniques. Brings valuable experience from developing hydrological models for Dutch water boards, ensuring alignment with user needs.
Niels Lafleur: Front-End Developer. An experienced developer specializing in creating intuitive and user-friendly graphical interfaces. Will be responsible for designing the Sand Tracer user interface, ensuring accessibility and ease of use.
Background of the company involved
HKV is an independent research and consultancy firm specializing in water and safety, known for innovative solutions in areas such as flood risk management, nature-based solutions, and coastal engineering. HKV holds a strong market position in the knowledge domain, bridging the gap between academic research and practical applications.
Relevant capabilities and experience:
Nature-based Solutions: HKV has extensive experience in developing and implementing Nature-based Solutions for coastal resilience, habitat restoration, and climate change adaptation.
Remote sensing: Expertise in processing and analysing satellite data for various applications, including land cover mapping, hydrological modelling, and environmental monitoring.
Data Science & AI: A dedicated team of data scientists and AI specialists with a proven track record in developing innovative solutions for water management, environmental monitoring, and risk assessment.
Existing products and services:
Early Warning Systems: HKV develops Early Warning Systems for floods, droughts, and other water-related hazards, utilizing remote sensing data and advanced modelling techniques.
Hydrological Models: Development of advanced hydrological models for water management, flood forecasting, and water resource assessment, incorporating both spatial and temporal data.
Coastal Engineering: Expertise in coastal processes, erosion assessment, and the design of coastal resilience measures, combining numerical modelling and field observations.
Vision
The Sand Tracer project aligns perfectly with HKV’s vision to be a leading innovator in applying data science and AI to address critical environmental challenges. The project contributes to HKV’s goals in several ways:
Advancement in data-driven solutions: Sand Tracer strengthens HKV’s capabilities in developing data-driven solutions for environmental monitoring and management, supporting the company’s ambition to be at the forefront of technological innovation.
Focus on Nature-Based Solutions: The project reinforces HKV’s commitment to nature-based approaches, demonstrating the potential of combining natural processes with advanced technologies for sustainable coastal management and biodiversity conservation.
International growth: Sand Tracer has the potential for international application, supporting HKV’s ambition to expand its services beyond the Netherlands and contribute to global environmental challenges.
Sand Tracer will also serve as a platform for internal knowledge development within HKV, encouraging collaboration between different teams and fostering expertise in cutting-edge technologies like AI and remote sensing.
Management part
Work breakdown
The project will adhere to the following work logic
WP 1000: Customer/user engagement: Focus on understanding user needs and requirements, identifying success criteria, and securing customer commitment for service utilization.
WP 2000: Technical feasibility: Address the technical development and implementation of the Sand Tracer service, including system architecture definition, building block characterization, and feasibility assessment.
WP 3000: Economic viability: Evaluate the economic aspects of the service, encompassing market analysis, competitive analysis, financial sustainability, and the development of a roadmap for implementation.
Schedule and milestones
The project will follow the proposed 6-month schedule, with key milestones aligned with the ESA Kick-Start guidelines.
Schedule:
- Project start: 2025-03-01
- Duration: 6 months
Milestones:
| ID | Title | Schedule Date (months) | Contributing Work Packages | Deliverables |
|---|---|---|---|---|
| KO | Kick-off Meeting (via tele-conference) | T0 | WP 1000, WP 2000, WP 3000 | |
| MTR | Mid-Term Review (via tele-conference) | T0 + 3 months | WP 1000, WP 2000, WP 3000 | Service Requirements (Intermediate); Service and System Architecture Definition (Intermediate); Business Plan (Intermediate) |
| FR | Final Review (ECSAT/ESTEC) | T0 + 6 months | WP 1000, WP 2000, WP 3000 | Service Requirements (Final); Service and System Architecture Definition (Final); Business Plan (Final); Final Report; Project Web Page |
Work package description (WPD)
The following table describes the working package regarding customer/user engagement:
| Project: Sand Tracer | WP: 1000 | |
| WP Title: Customer/user Engagement Company: HKV WP Manager: Michelle Rudolph Start Event: KO Planned Date: … End Event: KO + 6 months Planned Date: … |
Sheet .. of .. Issue ref .. Issue date .. |
|
| Objectives
To understand customer/user needs, define service requirements, identify success criteria, and secure customer commitment. Tasks:
|
||
The following table describes the working package regarding technical feasibility:
| Project: Sand Tracer | WP: 2000 | |
| WP Title: Technical Feasibility Company: HKV WP Manager: Mattijn van Hoek Start Event: KO Planned Date: … End Event: KO + 6 months Planned Date: … |
Sheet .. of .. Issue ref .. Issue date .. |
|
| Objectives
To define the service and system architecture, assess technical feasibility, and identify technical risks. Tasks:
|
||
The following table describes the working package regarding economic viability:
| Project: Sand Tracer | WP: 3000 | |
| WP Title: Economic viability Company: HKV WP Manager: Mattijn van Hoek Start Event: KO Planned Date: … End Event: KO + 6 months Planned Date: … |
Sheet .. of .. Issue ref .. Issue date .. |
|
| Objectives
To assess the economic viability of the Sand Tracer service, analyse market opportunities, and develop a roadmap for implementation and exploitation. Tasks:
|
||
Deliverable documentation
| ID | Title | Schedule Date (months) | Contributing Work Packages | Deliverables |
|---|---|---|---|---|
| KO | Kick-off Meeting (via tele-conference) | T0 | WP 1000, WP 2000, WP 3000 | |
| MTR | Mid Term Review (via tele-conference) | T0 + 3 months | WP 1000, WP 2000, WP 3000 | Service Requirements (Intermediate); Service and System Architecture Definition (Intermediate); Business Plan (Intermediate) |
| FR | Final Review (ECSAT/ESTEC) | T0 + 6 months | WP 1000, WP 2000, WP 3000 | Service Requirements (Final); Service and System Architecture Definition (Final); Business Plan (Final); Final Report; Project Web Page |
The project will deliver the following documentation as per ESA Kick-Start requirements:
Service requirements: Detailed documentation outlining the functional and technical requirements of the Sand Tracer service, based on user needs and feedback.
Service and system architecture definition: A comprehensive description of the service architecture, including system components, data flow, and interfaces.
Business plan: A detailed plan outlining the market analysis, competitive landscape, value proposition, financial projections, and roadmap for service implementation.
Final report: A concise report summarizing the project’s achievements, key findings, and recommendations for future development.
Project web page: A public web page providing information about the project, its objectives, and results.